OCS-14 : You can get Occluded in Fourteen Ways
Prithwijit Guha, Venkatesh Subramanian and amitabha mukerjee
Occlusions are a central phenomenon among interacting objects (e.g. for multi-object tracking in computer vision). However, formal analyses proposed in the spatial reasoning literature ignore many distinctions crucial to computer vision, as a result of which these algebras have been largely ignored in vision applications. Two distinctions of relevance to visual computation are (a) whether the occluder is a moving object or part of the static background, and (b) whether the visible part of a single object forms a single connected blob or not. In this work, we develop a formal model of occlusion states that handles these criteria with those proposed in spatial reasoning to come up with a comprehensive set of fourteen occlusion states. Transitions between these occlusion states are an important source of information on visual activity (e.g. splits and merges). We show that the resulting formalism is representationally complete in the sense that these states constitute a partition of all possible occlusion situations based on these criteria. Finally, we show results from implementations of this approach in a test application involving static camera based scene analysis, where occlusion state analysis and multiple object tracking can be used for two tasks - (a) identifying static occluders in the scene, and (b) modeling a class of interactions represented as transitions of occlusion states. Thus, the formalism is shown to have direct relevance to actual vision applications.